Natural language processing for storytelling and role playing: a training system based on the Propp model

Reading, understanding, writing and re-writing stories, playing different roles are considered powerful strategies for sharing human knowledge. The system developed in this paper, based on Propp's theory of folk tales and on Natural Language Processing techniques, is able to recognize main characters of folk tales, providing a summary of the text, and permitting users to edit the story in a controlled way. The list of main characters, as well as the summary, highlight the structure of the story, allowing students to easily understand its plot. Once students understood the story, they can modify it, editing the parts of the text where main characters play their own roles. This way, students can create new stories, starting from the original one and respecting its ground structure. The proposed model is not only based on word frequencies, and therefore is able to recognize characters even if the related words are not frequent in the text. The proposed algorithm has been compared with pure statistical predictors, observing that the proposed approach significantly outperform them